Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the presence of personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "I'm"

    np_acts-logits-general · gemini-2.0-flash

    i'm + state/opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.93
     ivelany
    -0.80
     betweenstory
    -0.74
    antMatchers
    -0.72
    WriteTagHelper
    -0.70
     المعيارى
    -0.68
     noastre
    -0.66
    URLException
    -0.65
     hini
    -0.65
     فريبيس
    -0.65
    POSITIVE LOGITS
     sure
    0.93
     sorry
    0.84
     glad
    0.73
     guessing
    0.71
     assuming
    0.67
     not
    0.65
     certainly
    0.62
     going
    0.60
     am
    0.56
     currently
    0.55
    Act Density 0.122%

    No Known Activations